NET_DMA: where do we ever call dma_skb_copy_datagram_iovec() with NULL pinned_list?

NET_DMA: where do we ever call dma_skb_copy_datagram_iovec() with NULL pinned_list?

[Al Viro]

	AFAICS, all callers of dma_skb_copy_datagram_iovec()
are either
	* recursive for fragments, pass pinned_list unchanged or
	* called from tcp, with pinned_list coming from
tp->ucopy.pinned_list and only when tp->ucopy.dma_chan is non-NULL.

Now, all non-NULL assignments to ->dma_chan have the same form:
	if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
		tp->ucopy.dma_chan = get_softnet_dma();
IOW, if ->ucopy.pinned_list stays NULL, ->ucopy.dma_chan will do the same.

Moreover, any place that resets ->ucopy.pinned_list will also reset
->ucopy.dma_chan.

IOW, we can't ever get non-NULL tp->ucopy.dma_chan while tp->ucopy.pinned_list
is NULL.  So how can we ever get to the dma_memcpy_to_kernel_iovec()?

Re: NET_DMA: where do we ever call dma_skb_copy_datagram_iovec() with NULL pinned_list?

[Andrew Grover]

On 7/20/07, Al Viro <viro@ftp.linux.org.uk> wrote:
>         AFAICS, all callers of dma_skb_copy_datagram_iovec()
> are either
>         * recursive for fragments, pass pinned_list unchanged or
>         * called from tcp, with pinned_list coming from
> tp->ucopy.pinned_list and only when tp->ucopy.dma_chan is non-NULL.
>
> Now, all non-NULL assignments to ->dma_chan have the same form:
>         if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
>                 tp->ucopy.dma_chan = get_softnet_dma();
> IOW, if ->ucopy.pinned_list stays NULL, ->ucopy.dma_chan will do the same.
>
> Moreover, any place that resets ->ucopy.pinned_list will also reset
> ->ucopy.dma_chan.
>
> IOW, we can't ever get non-NULL tp->ucopy.dma_chan while tp->ucopy.pinned_list
> is NULL.  So how can we ever get to the dma_memcpy_to_kernel_iovec()?

Shannon what do you think? Is this a bug, or does it no longer support
non-userspace iovecs?

Thanks -- Andy

RE: NET_DMA: where do we ever call dma_skb_copy_datagram_iovec() with NULL pinned_list?

[Nelson, Shannon]

Al Viro:
>
>	AFAICS, all callers of dma_skb_copy_datagram_iovec()
>are either
>	* recursive for fragments, pass pinned_list unchanged or
>	* called from tcp, with pinned_list coming from
>tp->ucopy.pinned_list and only when tp->ucopy.dma_chan is non-NULL.
>
>Now, all non-NULL assignments to ->dma_chan have the same form:
>	if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
>		tp->ucopy.dma_chan = get_softnet_dma();
>IOW, if ->ucopy.pinned_list stays NULL, ->ucopy.dma_chan will 
>do the same.
>
>Moreover, any place that resets ->ucopy.pinned_list will also reset
>->ucopy.dma_chan.
>
>IOW, we can't ever get non-NULL tp->ucopy.dma_chan while 
>tp->ucopy.pinned_list
>is NULL.  So how can we ever get to the dma_memcpy_to_kernel_iovec()?

It looks like this is "extra" code.  The history seems to be that it was
thought to be useful for internal copying, perhaps for smbfs or iSCSI,
as the comment suggests.  However, since no one is using it, it can
probably come out.  If there is no argument, I'll post a patch to remove
it.

sln
--
======================================================================
Mr. Shannon Nelson                 LAN Access Division, Intel Corp.
Shannon.Nelson@intel.com                I don't speak for Intel
(503) 712-7659                    Parents can't afford to be squeamish.